Skip to main content
MIT AI Risk Initiative
BackStereotype Bias
Home/Risks/Liu et al. (2024)/Stereotype Bias
Injustice
Preference Bias

Stereotype Bias

Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment

Liu et al. (2024)

SourceDOI
Sub-category
Risk Domain
1Discrimination & Toxicity
1.1Unfair discrimination and misrepresentation

Unequal treatment of individuals or groups by AI, often based on race, gender, or other sensitive characteristics, resulting in unfair outcomes and unfair representation of those groups.

LLMs must not exhibit or highlight any stereotypes in the generated text. Pretrained LLMs tend to pick up stereotype biases persisting in crowdsourced data and further amplify them(p. 17)

Entity— Who or what caused the harm

Human

Due to a decision or action made by humans

AI system

Due to a decision or action made by an AI system

Other

Due to some other reason or is ambiguous

Intent— Whether the harm was intentional or accidental

Intentional

Due to an expected outcome from pursuing a goal

Unintentional

Due to an unexpected outcome from pursuing a goal

Other

Without clearly specifying the intentionality

Timing— Whether the risk is pre- or post-deployment

Pre-deployment

Occurring before the AI is deployed

Post-deployment

Occurring after the AI model has been trained and deployed

Other

Without a clearly specified time of occurrence

Part of Fairness

Other risks from Liu et al. (2024) (34)

Reliability

3.1 False or misleading information
AI systemUnintentionalPost-deployment

Reliability > Misinformation

3.1 False or misleading information
AI systemUnintentionalPost-deployment

Reliability > Hallucination

3.1 False or misleading information
AI systemUnintentionalPost-deployment

Reliability > Inconsistency

7.3 Lack of capability or robustness
AI systemUnintentionalPost-deployment

Reliability > Miscalibration

3.1 False or misleading information
AI systemUnintentionalPost-deployment

Reliability > Sychopancy

3.1 False or misleading information
AI systemIntentionalPost-deployment
View all 34 risks from this paper →